{"id":"https://openalex.org/W3129799391","doi":"https://doi.org/10.1109/icassp39728.2021.9414979","title":"Multimodal Punctuation Prediction with Contextual Dropout","display_name":"Multimodal Punctuation Prediction with Contextual Dropout","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3129799391","doi":"https://doi.org/10.1109/icassp39728.2021.9414979","mag":"3129799391"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.11012","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102853619","display_name":"Andrew Silva","orcid":"https://orcid.org/0000-0002-0317-5135"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Silva","raw_affiliation_strings":["Georgia Institute of Technology","#N#\u2021#N#Georgia Institute of Technology#N#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"#N#\u2021#N#Georgia Institute of Technology#N#","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112911728","display_name":"Barry-John Theobald","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]},{"id":"https://openalex.org/I4210141230","display_name":"Apple (Germany)","ror":"https://ror.org/03fjbw519","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210141230","https://openalex.org/I4210153776"]}],"countries":["DE","GB"],"is_corresponding":false,"raw_author_name":"Barry-John Theobald","raw_affiliation_strings":["Apple","[Apple]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]},{"raw_affiliation_string":"[Apple]","institution_ids":["https://openalex.org/I4210141230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071541814","display_name":"Nicholas Apostoloff","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]},{"id":"https://openalex.org/I4210141230","display_name":"Apple (Germany)","ror":"https://ror.org/03fjbw519","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210141230","https://openalex.org/I4210153776"]}],"countries":["DE","GB"],"is_corresponding":false,"raw_author_name":"Nicholas Apostoloff","raw_affiliation_strings":["Apple","[Apple]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]},{"raw_affiliation_string":"[Apple]","institution_ids":["https://openalex.org/I4210141230"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"24","issue":null,"first_page":"3980","last_page":"3984"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/punctuation","display_name":"Punctuation","score":0.880577564239502},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8060760498046875},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.6616398096084595},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6107462048530579},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5556822419166565},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5407474040985107},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4617564380168915},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.4532044231891632},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4263579845428467},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4100610017776489},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34922102093696594},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0782899558544159}],"concepts":[{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.880577564239502},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8060760498046875},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6616398096084595},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6107462048530579},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5556822419166565},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5407474040985107},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4617564380168915},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.4532044231891632},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4263579845428467},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4100610017776489},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34922102093696594},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0782899558544159},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.11012","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.11012","pdf_url":"https://arxiv.org/pdf/2102.11012","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3129799391","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2102.11012","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2102.11012","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.11012","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/4rhy-3h65","is_oa":true,"landing_page_url":"https://doi.org/10.17023/4rhy-3h65","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.11012","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.11012","pdf_url":"https://arxiv.org/pdf/2102.11012","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3129799391.pdf","grobid_xml":"https://content.openalex.org/works/W3129799391.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1587490638","https://openalex.org/W2153579005","https://openalex.org/W2166116787","https://openalex.org/W2184135559","https://openalex.org/W2250539671","https://openalex.org/W2395173459","https://openalex.org/W2397873193","https://openalex.org/W2398104528","https://openalex.org/W2403334028","https://openalex.org/W2406343628","https://openalex.org/W2575282817","https://openalex.org/W2612007440","https://openalex.org/W2705373224","https://openalex.org/W2810621157","https://openalex.org/W2938722449","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963425185","https://openalex.org/W2965373594","https://openalex.org/W2980282514","https://openalex.org/W3037101098","https://openalex.org/W3045571807","https://openalex.org/W3046609253","https://openalex.org/W3094965760","https://openalex.org/W6635223454","https://openalex.org/W6682691769","https://openalex.org/W6684662674","https://openalex.org/W6686282164","https://openalex.org/W6712411474","https://openalex.org/W6713441181","https://openalex.org/W6713490458","https://openalex.org/W6731992975","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6766673545"],"related_works":["https://openalex.org/W3160489181","https://openalex.org/W3039572191","https://openalex.org/W3046609253","https://openalex.org/W3082144843","https://openalex.org/W3203803655","https://openalex.org/W2903250132","https://openalex.org/W2950548836","https://openalex.org/W606542161","https://openalex.org/W3105804405","https://openalex.org/W3015747801","https://openalex.org/W2886319145","https://openalex.org/W2995732811","https://openalex.org/W3161525333","https://openalex.org/W3003335331","https://openalex.org/W3094180720","https://openalex.org/W3034931686","https://openalex.org/W2618015847","https://openalex.org/W2250628345","https://openalex.org/W2916586819","https://openalex.org/W2173905402"],"abstract_inverted_index":{"Automatic":[0],"speech":[1],"recognition":[2],"(ASR)":[3],"is":[4,23],"widely":[5],"used":[6],"in":[7,32,34],"consumer":[8],"electronics.":[9],"ASR":[10],"greatly":[11],"improves":[12],"the":[13,21,51,57,61,82,94],"utility":[14],"and":[15,75,96],"accessibility":[16],"of":[17,60,117],"technology,":[18],"but":[19],"usually":[20],"output":[22],"only":[24],"word":[25],"sequences":[26],"without":[27],"punctuation.":[28],"This":[29],"can":[30],"result":[31],"ambiguity":[33],"inferring":[35],"user-intent.":[36],"We":[37,64],"first":[38],"present":[39,100],"a":[40,105],"transformer-based":[41],"approach":[42,102],"for":[43,89],"punctuation":[44],"prediction":[45],"that":[46,70,110],"achieves":[47,78],"8%":[48,79],"improvement":[49,80],"on":[50,85],"IWSLT":[52],"2012":[53],"TED":[54],"Task,":[55],"beating":[56],"previous":[58],"state":[59],"art":[62],"[1].":[63],"next":[65],"describe":[66],"our":[67],"multimodal":[68],"model":[69,106],"learns":[71],"from":[72],"both":[73,93],"text":[74],"audio,":[76],"which":[77,90],"over":[81],"text-only":[83],"algorithm":[84],"an":[86,101],"internal":[87],"dataset":[88],"we":[91,99],"have":[92],"audio":[95],"transcriptions.":[97],"Finally,":[98],"to":[103,113],"learning":[104],"using":[107],"contextual":[108],"dropout":[109],"allows":[111],"us":[112],"handle":[114],"variable":[115],"amounts":[116],"future":[118],"context":[119],"at":[120],"test":[121],"time.":[122]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}